Overview

​

Installation

To install the latest version, use either of the following:

​

Authentication

You will need an API key to use our SDKs; get it from your account page.

​

Quick Start

To start synthesizing speech right away, check out our general Getting Started guide. There you’ll see how to set up your environment and run through some sample code examples for text-to-speech and streaming.

​

Next.js and Edge Runtime

This SDK is compatible with Next.js and the Edge Runtime. To use it in a Next.js project, you will need to add the following to your next.config.js file:

webpack: (config, { isServer }) => {
    // Only run this on the server
    if (isServer) {
      config.resolve.fallback = config.resolve.fallback || {};
      config.resolve.fallback.fs = false;
    }

    return config;
  },

The createVoice() method uses the fs module, which is not available in the Edge Runtime. While the SDK automatically disables this method in non-Node.js environments, this code snippet will prevent the build from failing when the fs module is not available.

Learn more about custom webpack configuration in Next.js here.

​